A new near-term breast cancer risk prediction scheme based on the quantitative analysis of ipsilateral view mammograms

Breast cancer incidence by age at discovery of mammographic abnormality in women participating in French organized screening campaigns

OBJECTIVE

Statistical modeling was already predicted the occurrence/prognosis of breast cancer from previous radiological findings. This study predicts the breast cancer risk by the age at discovery of mammographic abnormality in the French breast cancer screening program.

STUDY DESIGN

This was a cohort study.

METHODS

The study included 261,083 women who meet the inclusion criteria: aged 50-74 years, living in French departments (Ain, Doubs, Haute-Saône, Jura, Territoire-de-Belfort, and Yonne), with at least two mammograms between January 1999 and December 2017, of which the first was 'normal/benign'. The incidence of each abnormality (microcalcifications, spiculated mass, obscured mass, architectural distortion, and asymmetric density) was first estimated, then the breast cancer risk was predicted secondly according to the age at discovery of each mammographic abnormality, using an actuarial life table and a Cox model.

RESULTS

Overall breast cancer (6326 cases) incidence was 3.3 (3.0; 3.1)/1000 person-years. The breast cancer incidence increased proportionally with the discovery age of the speculated mass and microcalcifications. The incidence was twice as high when the spiculated mass age of discovery was ≥70 (12.2 [10.4; 14.4]) compared with age 50-54 years (5.8 [5.1; 6.7]). Depending on the spiculated mass discovery age, the breast cancer risk increased by at least 40% between the age groups 55-59 years (1.4 [1.0; 1.8]) and ≥70 years (2.4 [1.9; 3.3]). Whatever the abnormality, the incidence of breast cancer was higher when it was present in only one breast.

CONCLUSION

The study highlights a stable incidence of breast cancer between successive mammograms, an increased risk of breast cancer with the finding age of spiculated mass and microcalcifications. The reduced delay between the abnormality discovery date and the breast cancer diagnosis date would justify a specific follow-up protocol after the finding of these two abnormalities.

Application of deep learning in the detection of breast lesions with four different breast densities

Objective

This retrospective study evaluated the model from populations with different breast densities and showed the model's performance on malignancy prediction.

Methods

A total of 608 mammograms were collected from Northern Jiangsu People's Hospital in Yangzhou City. The data from this province have not been used in the training or evaluation data set.

The model consists of three submodules, lesion detection (Mask‐rcnn), lesion registration between craniocaudal view and mediolateral oblique view, malignancy prediction network (ResNet). The data set used to train the model was obtained from nine institutions across six cities. For normal cases, there were no annotations. Here, we adopted the free‐response receiver operating characteristic (FROC) curve as the indicator to evaluate the detection performance of all cancers and triple‐negative breast cancer (TNBC). The FROC curves are also shown for mass/distortion/asymmetry and typical benign calcification in two kinds of populations with four types of breast density.

Results

The sensitivity to mass/distortion/asymmetry for the four types of breast (A, B, C, D) are 0.94, 0.92, 0.89, and 0.72, respectively, when false positive per image is 0.25, while these values are 1.00, 0.95, 0.92, and 0.90, respectively, for the amorphous calcification lesions. The sensitivity for the cancer is 0.85 at the same false‐positive rate. The TNBC accounts for about 10%–20% of all breast cancers and is more aggressive with poor prognosis than other breast cancers. Herein, we also evaluated performance on the TNBC cases. Our results show that Yizhun AI could detect 75% TNBC lesions at the same false‐positive level mentioned above.

Conclusion

The Yizhun AI model used in our work has good diagnostic efficiency for different types of breast, even for the extremely dense breast. It has a guiding role in the clinical diagnosis of breast cancer. The performance of Yizhun AI on mass/distortion/asymmetry is affected by breast density significantly compared to that on amorphous calcification.

A novel approach for breast cancer prediction using optimized ANN classifier based on big data environment

Cancer is caused by the un-controlled division of abnormal cells in a body part. Various cancers exist in this world and one amongst them is breast cancer. Breast cancer (BC) threatens the lives of people and today, it is the secondary prime cause of death in women. Numerous research directions concentrated on the prediction of BC. The prevailing prediction model is time-consuming and have less accuracy. To trounce those drawbacks, this paper proposed a BC prediction system (BCPS) utilizing Optimized Artificial Neural Network (OANN). Primarily, the unprocessed BC data are regarded as the input. The big data (BD) storage comprises some repeated information. Secondarily, such repeated data are eliminated by utilizing Hadoop MapReduce. In the subsequent stage, the data are preprocessed utilizing replacing of missing attributes (RMA) and normalization techniques. Subsequently, the features are generally chosen by utilizing Modified Dragonfly algorithm (MDF). Then, the selected features are inputted for classification. Here, it classifies the features utilizing OANN. Optimization is done by employing the Gray Wolf Optimization (GWO) algorithm. Experiential outcomes are contrasted with prevailing IWDT (Improved Weighted-Decision Tree) in respect of precision, recall, accuracy, and ROC.

Global parenchymal texture features based on histograms of oriented gradients improve cancer development risk estimation from healthy breasts

BACKGROUND

The breast dense tissue percentage on digital mammograms is one of the most commonly used markers for breast cancer risk estimation. Geometric features of dense tissue over the breast and the presence of texture structures contained in sliding windows that scan the mammograms may improve the predictive ability when combined with the breast dense tissue percentage.

METHODS

A case/control study nested within a screening program covering 1563 women with craniocaudal and mediolateral-oblique mammograms (755 controls and the contralateral breast mammograms at the closest screening visit before cancer diagnostic for 808 cases) aging 45 to 70 from Comunitat Valenciana (Spain) was used to extract geometric and texture features. The dense tissue segmentation was performed using DMScan and validated by two experienced radiologists. A model based on Random Forests was trained several times varying the set of variables. A training dataset of 1172 patients was evaluated with a 10-stratified-fold cross-validation scheme. The area under the Receiver Operating Characteristic curve (AUC) was the metric for the predictive ability. The results were assessed by only considering the output after applying the model to the test set, which was composed of the remaining 391 patients.

RESULTS

The AUC score obtained by the dense tissue percentage (0.55) was compared to a machine learning-based classifier results. The classifier, apart from the percentage of dense tissue of both views, firstly included global geometric features such as the distance of dense tissue to the pectoral muscle, dense tissue eccentricity or the dense tissue perimeter, obtaining an accuracy of 0.56. By the inclusion of a global feature based on local histograms of oriented gradients, the accuracy of the classifier was significantly improved (0.61). The number of well-classified patients was improved up to 236 when it was 208.

CONCLUSION

Relative geometric features of dense tissue over the breast and histograms of standardized local texture features based on sliding windows scanning the whole breast improve risk prediction beyond the dense tissue percentage adjusted by geometrical variables. Other classifiers could improve the results obtained by the conventional Random Forests used in this study.